Open wdr123 opened 5 months ago
Thanks for your help.
On Tue, May 7, 2024 at 8:52 AM Matthias Fey @.***> wrote:
You can find the torch.nn.Module implementation here https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/conv/spline_conv.py, which should work fine both for CPU and CUDA usage.
For batching, we follow PyG's mini-batch structure, see here https://pytorch-geometric.readthedocs.io/en/latest/advanced/batching.html for an explanation.
— Reply to this email directly, view it on GitHub https://github.com/rusty1s/pytorch_spline_conv/issues/50#issuecomment-2098336957, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHW3K7KRPB7QX5DEPNZAIKTZBDFBRAVCNFSM6AAAAABGZSFG26VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJYGMZTMOJVG4 . You are receiving this because you authored the thread.Message ID: @.***>
Hi authors, thanks for this amazing work. My question is when I try to put the model's parameter in cuda mode, the spline_conv doesn't work and inform me parameters (weights) must be in cpu mode. Also spline_conv seems doesn't support batch as the input tensor's first dimension like other NN's forwarding function. Is that true? If it is, how can we achieve data parallel on GPU with spline_conv(.)? Thanks.